@inproceedings{huang-etal-2026-sherry,
    title = "Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification",
    author = "Huang, Hong  and
      Wu, Decheng  and
      Hu, Qiangqiang  and
      Yu, Guanghua  and
      Yang, Jinhai  and
      Zhu, Jianchen  and
      Liu, Xue  and
      Wu, Dapeng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.513/",
    pages = "11186--11204",
    ISBN = "979-8-89176-390-6"
}